Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 4259
    Prev
    Next
    INDEX
    Explanations

    mathematical structures and expressions involving variables, functions, and indices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }^{
    -0.90
    }^{\
    -0.85
    }^{-
    -0.82
    }^{(
    -0.74
    )}^{
    -0.72
    IndentedString
    -0.63
    }^
    -0.63
    }^{*}
    -0.61
    }^{*}$
    -0.60
    </sub>
    -0.60
    POSITIVE LOGITS
    </sup>
    0.87
     *}
    0.63
     *}$
    0.61
    kháu
    0.49
    __;
    0.48
    *}[
    0.47
    дравствуйте
    0.46
    rahat
    0.46
    anças
    0.45
    //
    0.45
    Activations Density 0.608%

    No Known Activations